mcp-pdf-tokensaver
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| inspect_pdf_structure | Analyze the layout and structural skeleton of a local PDF file without fetching full text. Identifies pages, multi-column blocks, headings, equations, and tables to save context token window. Use this first to understand the document structure before fetching specific content. |
| fetch_pdf_chunksA | Selectively fetch the raw, highly-structured text paragraphs or equations of specific blocks based on their blockId. Use this after inspect_pdf_structure to pull only the necessary data chunks. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no ambiguity. The tool's purpose is clear and distinct by default.
The single tool follows a clear verb_noun pattern (fetch_pdf_chunks), which is consistent within the set.
A single tool is too few for a PDF processing server, especially since it references a missing tool (inspect_pdf_structure) that is essential for its intended workflow.
The server's sole tool cannot function as intended without a prerequisite tool for PDF structure inspection. This is a severe completeness gap.